© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54996
    Prev
    Next
    INDEX
    Explanations

    years between 1950-1960

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slice
    -0.10
    æĶ¹éĿ©å¼ĢæĶ¾
    -0.10
    ç¢İ
    -0.09
    èĦ±èIJ½
    -0.09
    碰æĴŀ
    -0.09
    踩
    -0.08
     Pru
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    æĿ¯
    -0.08
    å°ijè§ģ
    -0.08
    POSITIVE LOGITS
    endo
    0.10
    ç¿»
    0.09
    ibia
    0.09
    peek
    0.08
     Truman
    0.08
     tween
    0.08
    宸
    0.08
    Ñĩик
    0.08
    eva
    0.08
     segregation
    0.08
    Activations Density 0.288%

    No Known Activations